Jinchuan Tian

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

2023 · arXiv (Cornell University)

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community remains constrained. One …

Preference Alignment Improves Language Model-Based TTS

2025

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust LMs to align with the preferences …

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

2025 · arXiv (Cornell University)

The Open Whisper-style Speech Models (OWSM) project has developed a series of fully open speech foundation models using academic-scale resources, but their training data remains insufficient. This work enhances OWSM by integrating YODAS, a large-scale …

Chain-of-Thought Training for Open E2E Spoken Dialogue Systems

2025 · arXiv (Cornell University)

Unlike traditional cascaded pipelines, end-to-end (E2E) spoken dialogue systems preserve full differentiability and capture non-phonemic information, making them well-suited for modeling spoken interactions. However, existing E2E approaches often require large-scale training data and generates responses …